@inproceedings{narayanan-sundararaman-etal-2020-unsupervised,
title = "Unsupervised Aspect-Level Sentiment Controllable Style Transfer",
author = "Narayanan Sundararaman, Mukuntha and
Ahmad, Zishan and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.33",
doi = "10.18653/v1/2020.aacl-main.33",
pages = "303--312",
abstract = "Unsupervised style transfer in text has previously been explored through the sentiment transfer task. The task entails inverting the overall sentiment polarity in a given input sentence, while preserving its content. From the Aspect-Based Sentiment Analysis (ABSA) task, we know that multiple sentiment polarities can often be present together in a sentence with multiple aspects. In this paper, the task of aspect-level sentiment controllable style transfer is introduced, where each of the aspect-level sentiments can individually be controlled at the output. To achieve this goal, a BERT-based encoder-decoder architecture with saliency weighted polarity injection is proposed, with unsupervised training strategies, such as ABSA masked-language-modelling. Through both automatic and manual evaluation, we show that the system is successful in controlling aspect-level sentiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="narayanan-sundararaman-etal-2020-unsupervised">
<titleInfo>
<title>Unsupervised Aspect-Level Sentiment Controllable Style Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mukuntha</namePart>
<namePart type="family">Narayanan Sundararaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zishan</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised style transfer in text has previously been explored through the sentiment transfer task. The task entails inverting the overall sentiment polarity in a given input sentence, while preserving its content. From the Aspect-Based Sentiment Analysis (ABSA) task, we know that multiple sentiment polarities can often be present together in a sentence with multiple aspects. In this paper, the task of aspect-level sentiment controllable style transfer is introduced, where each of the aspect-level sentiments can individually be controlled at the output. To achieve this goal, a BERT-based encoder-decoder architecture with saliency weighted polarity injection is proposed, with unsupervised training strategies, such as ABSA masked-language-modelling. Through both automatic and manual evaluation, we show that the system is successful in controlling aspect-level sentiments.</abstract>
<identifier type="citekey">narayanan-sundararaman-etal-2020-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2020.aacl-main.33</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.33</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>303</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Aspect-Level Sentiment Controllable Style Transfer
%A Narayanan Sundararaman, Mukuntha
%A Ahmad, Zishan
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F narayanan-sundararaman-etal-2020-unsupervised
%X Unsupervised style transfer in text has previously been explored through the sentiment transfer task. The task entails inverting the overall sentiment polarity in a given input sentence, while preserving its content. From the Aspect-Based Sentiment Analysis (ABSA) task, we know that multiple sentiment polarities can often be present together in a sentence with multiple aspects. In this paper, the task of aspect-level sentiment controllable style transfer is introduced, where each of the aspect-level sentiments can individually be controlled at the output. To achieve this goal, a BERT-based encoder-decoder architecture with saliency weighted polarity injection is proposed, with unsupervised training strategies, such as ABSA masked-language-modelling. Through both automatic and manual evaluation, we show that the system is successful in controlling aspect-level sentiments.
%R 10.18653/v1/2020.aacl-main.33
%U https://aclanthology.org/2020.aacl-main.33
%U https://doi.org/10.18653/v1/2020.aacl-main.33
%P 303-312
Markdown (Informal)
[Unsupervised Aspect-Level Sentiment Controllable Style Transfer](https://aclanthology.org/2020.aacl-main.33) (Narayanan Sundararaman et al., AACL 2020)
ACL
- Mukuntha Narayanan Sundararaman, Zishan Ahmad, Asif Ekbal, and Pushpak Bhattacharyya. 2020. Unsupervised Aspect-Level Sentiment Controllable Style Transfer. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 303–312, Suzhou, China. Association for Computational Linguistics.